Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Paper
•
2505.14669
•
Published
•
77
Rush Tabesh
soroushtabesh
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
27 days ago
Bridging the Gap Between Promise and Performance for Microscaling FP4
Quantization
upvoted
a
paper
3 months ago
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane
Algorithm
upvoted
a
paper
5 months ago
SVD-Free Low-Rank Adaptive Gradient Optimization for Large Language
Models
Organizations
authored
a
paper
5 months ago
authored
2
papers
9 months ago